Intermediate Deep Feature Compression: the Next Battlefield of Intelligent Sensing
This work addresses the problem of efficient collaboration between front-end and cloud servers for large-scale visual analysis, though it appears incremental as it builds on existing compression methods.
The paper tackles the challenge of enabling intelligent sensing at the front-end by proposing to compress and transmit intermediate-layer deep learning features, achieving a balance between computational load, transmission load, and generalization ability for cloud-based visual analysis.
The recent advances of hardware technology have made the intelligent analysis equipped at the front-end with deep learning more prevailing and practical. To better enable the intelligent sensing at the front-end, instead of compressing and transmitting visual signals or the ultimately utilized top-layer deep learning features, we propose to compactly represent and convey the intermediate-layer deep learning features of high generalization capability, to facilitate the collaborating approach between front and cloud ends. This strategy enables a good balance among the computational load, transmission load and the generalization ability for cloud servers when deploying the deep neural networks for large scale cloud based visual analysis. Moreover, the presented strategy also makes the standardization of deep feature coding more feasible and promising, as a series of tasks can simultaneously benefit from the transmitted intermediate layers. We also present the results for evaluation of lossless deep feature compression with four benchmark data compression methods, which provides meaningful investigations and baselines for future research and standardization activities.